tmt_sim: Function for the Simulation of Multistage-Designs

In tmt: Estimation of the Rasch Model for Multistage Tests

Function for the Simulation of Multistage-Designs

Description

This function simulates data according to the specified and submitted multistage design. The persons are drawn from a standard normal distribution if the amount of persons are specified. As an additional argument, a seed can also be set. If requested, it is also possible to submit a vector ore list of person parameters to specify different person distributions.

Usage

tmt_sim(
  mstdesign = NULL,
  items = NULL,
  persons = NULL,
  preconditions = NULL,
  ...
)

Arguments

mstdesign	definition of desired multistage design
items	vector of difficulty parameters for each items
persons	amount of persons per starting module
preconditions	definition of preconditions can optionally be specified. In the case of probabilistic routing preconditions such as a pre-test, which are taken into account in the MST design. For the specification the correlation with the true person parameter have to be specified. The submitted correlation is adjusted in the function according to Demirtas and Yavuz (2015; <doi:10.1080/10543406.2014.920868>) It is also possible to submit your own vector with integers for the preconditions.
...	further optional arguments like setting a seed

Value

List with following entries

data	Matrix with item responses
data_mst	Data frame with item responses and additional a vector of used modules per person
persons	Generated and used person parameters
mstdesign	Submitted multistage design

Author(s)

Jan Steinfeld

References

• Demirtas, H., & Yavuz, Y. (2015). Concurrent Generation of Ordinal and Normal Data. Journal of Biopharmaceutical Statistics, 25(4), 635-650. https://doi.org/10.1080/10543406.2014.920868

Examples

#############################################################################
# translate multistage model 1
#############################################################################
 mstdesign <- "
	 M1 =~ c(i1, i2, i3, i4, i5)
	 M2 =~ c(i6, i7, i8, i9, i10)
	 M3 =~ c(i11, i12, i13, i14, i15)

	 # define branches
	 p1 := M2(0,2) + M1
	 p2 := M2(3,5) + M3
 "
items <- seq(-3,3,length.out = 15)
names(items) <- paste0("i", seq(items))

data_1 <- tmt_sim(mstdesign = mstdesign, 
    items = items, 
    persons = 500, 
    seed = 1111)

#############################################################################
# translate multistage model 2
#############################################################################
mstdesign <- "
    M1 =~ c(i1, i2, i3, i4, i5)
    M2 =~ c(i6, i7, i8, i9, i10)
    M3 =~ c(i11, i12, i13, i14, i15)
    M4 =~ c(i16, i17, i18, i19, i20)
    M5 =~ c(i21, i22, i23, i24, i25)
    M6 =~ c(i26, i27, i28, i29, i30)

    # define branches
    p1 := M4(0,2) + M2(0,2) + M1
    p2 := M4(0,2) + M2(3,5) + M3
    p3 := M4(3,5) + M5(0,2) + M3
    p4 := M4(3,5) + M5(3,5) + M6
  "

items <- seq(-3,3,length.out = 30)
names(items) <- paste0("i", seq(items))

data_2 <- tmt_sim(mstdesign = mstdesign, 
    items = items, 
    persons = 500,
    seed = 1111)

tmt documentation built on May 17, 2022, 5:09 p.m.